Table 2 Comparison of performances of Random Forest (RF) and k-Nearest Neighbors (k-NN) classifiers in terms of number of predicted annotations (N), their precision (Pr) and the average level (\(\overline {L}\)) of predicted annotation terms in the Gene Ontology DAG (when the term of a predicted annotation belongs to multiple Gene Ontology levels, only its lowest level was considered). SM is the single model method; AVG considers the average of the likelihood scores given by the models inferred from five different perturbation random seeds; ∩_x/5 considers those predictions from x out of the five models. Probability of perturbation p and likelihood threshold ρ were set to their respective default values p=10% and ρ=0.8

2,285

0.908

1.604

2,841

0.803

1.864

1,204

0.952

1.799

1,227

0.817

2.487

4,753

0.826

1.736

6,378

0.704

1.888

2,896

0.916

1.653

3,380

0.836

1.826

2,157

0.947

1.569

2,396

0.911

1.734

1,764

0.973

1.491

1,499

0.937

1.774

932

0.987

1.626

552

0.955

2.317

132

0.874

2.721

123

0.657

2.835

57

0.947

3.037

44

0.568

3.000

373

0.794

2.544

355

0.625

2.725

173

0.925

2.831

155

0.710

2.864

100

0.960

2.854

62

0.726

3.022

60

0.967

2.931

32

0.656

3.238

37

0.946

3.143

13

0.462

3.500

69

0.721

2.701

50

0.534

3.255

36

0.833

3.367

29

0.690

3.800

175

0.617

2.157

137

0.416

2.509

88

0.682

2.700

55

0.564

3.290

56

0.857

2.958

31

0.742

3.652

38

0.895

3.324

17

0.765

4.308

24

0.917

3.545

11

0.909

5.000

966

0.846

2.522

1,029

0.718

2.651

773

0.906

2.500

869

0.794

2.733

1,917

0.741

2.454

2,108

0.574

2.518

1,334

0.833

2.531

1,233

0.737

2.664

997

0.872

2.517

858

0.830

2.718

760

0.905

2.529

622

0.883

2.703

444

0.941

2.555

326

0.951

2.900